The deep neural network has found widespread application in object detection due to its high accuracy. However, its performance typically depends on the availability of a substantial volume of accurately labeled data. Several active learning approaches have been proposed to reduce the labeling dependency based on the confidence of the detector. Nevertheless, these approaches tend to exhibit biases toward high-performing classes, resulting in datasets that do not adequately represent the testing data. In this study, we introduce a comprehensive framework for active learning that considers both the uncertainty and the robustness of the detector, ensuring superior performance across all classes. The robustness-based score for active learning is calculated using the consistency between an image and its augmented version. Additionally, we leverage pseudo-labeling to mitigate potential distribution drift and enhance model performance. To address the challenge of setting the pseudo-labeling threshold, we introduce an adaptive threshold mechanism. This adaptability is crucial, as a fixed threshold can negatively impact performance, particularly for low-performing classes or during the initial stages of training. For our experiment, we employ the Southeast Area Monitoring and Assessment Program Dataset 2021 (SEAMAPD21), comprising 130 fish species classes with 28,328 image samples. The results show that our model outperforms the state-of-the-art method and significantly reduces the annotation cost. Furthermore, we benchmark our model’s performance against a public dataset (PASCAL VOC07), showcasing its effectiveness in comparison to existing methods.
Fish species must be identified for stock assessments, ecosystem monitoring, production management, and the conservation of endangered species. Implementing algorithms for fish species detection in underwater settings like the Gulf of Mexico poses a formidable challenge. Active learning, a method that efficiently identifies informative samples for annotation while staying within a budget, has demonstrated its effectiveness in the context of object detection in recent times. In this study, we present an active detection model designed for fish species recognition in underwater environments. This model can be employed as an object detection system to effectively lower the expense associated with manual annotation. It uses epistemic uncertainty with Evidential Deep Learning (EDL) and proposes a novel module denoted as Model Evidence Head (MEH) for fish species detection in underwater environments. It employs Hierarchical Uncertainty Aggregation (HUA) to obtain the informativeness of an image. We conducted experiments using a fine-grained and extensive dataset of reef fish collected from the Gulf of Mexico, specifically the Southeast Area Monitoring and Assessment Program Dataset 2021 (SEAMAPD21). The experimental results demonstrate that an active detection framework achieves better detection performance on the SEAMAPD21 dataset demonstrating a favorable balance between performance and data efficiency for underwater fish species recognition.
Video surveys are commonly used to monitor the abundance and distribution of managed species to support management. However, considerable effort, time, and cost are required for human review and automated fish species recognition provides an effective solution to remove the bottleneck of post-processing. Implementing fish species detection techniques for underwater imagery is a challenging task. In this work, we present the Multiple Instance Active-learning for Fish-species Recognition (MI-AFR), which is formulated as an object detection-based approach to perform localization and classification of fish species. It can select the most informative fish images from unlabeled sets by estimating the uncertainty of unlabeled images by using adversarial classifiers trained on labeled sets. Moreover, we have analyzed the improved performance of MI-AFR by considering different backbone networks as a trade-off between speed and accuracy. For experiments, we have used the fine-grained and large-scale reef fish dataset obtained from the Gulf of Mexico – the Southeast Area Monitoring and Assessment Program Dataset 2021 (SEAMAPD21). The experimental results illustrate that the superiority of the proposed method can establish a solid foundation for active learning in fish species recognition, especially with a small number of labeled sets.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.